Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abulary
    -0.73
    umatic
    -0.70
    avorite
    -0.68
    itech
    -0.68
     hypoc
    -0.66
    atche
    -0.66
    habi
    -0.65
    ffield
    -0.65
    eous
    -0.64
    oso
    -0.64
    POSITIVE LOGITS
    NPR
    0.72
    Correction
    0.72
    ror
    0.68
    rob
    0.68
    Elizabeth
    0.65
    kill
    0.63
     lantern
    0.62
    mun
    0.62
    ml
    0.61
    mos
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.